English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Text-to-image diffusion models are gradually introduced into computergraphics, recently enabling the development of Text-to-3D pipelines in an opendomain. However, for interactive editing purposes, local manipulations ofcontent through a simplistic textual interface can be arduous. Incorporatinguser guided sketches with Text-to-image pipelines offers users more intuitivecontrol. Still, as state-of-the-art Text-to-3D pipelines rely on optimizingNeural Radiance Fields (NeRF) through gradients from arbitrary rendering views,conditioning on sketches is not straightforward. In this paper, we presentSKED, a technique for editing 3D shapes represented by NeRFs. Our techniqueutilizes as few as two guiding sketches from different views to alter anexisting neural field. The edited region respects the prompt semantics througha pre-trained diffusion model. To ensure the generated output adheres to theprovided sketches, we propose novel loss functions to generate the desirededits while preserving the density and radiance of the base instance. Wedemonstrate the effectiveness of our proposed method through severalqualitative and quantitative experiments. https://sked-paper.github.io/

SKED: Sketch-guided Text-based 3D Editing